Risk factors for in-hospital heart failure in patients with acute myocardial infarction and construction of predictive models.

Objective: To identify risk factors and develop a predictive model for heart failure in patients with acute myocardial infarction (AMI).

Methods: Clinical data from 312 AMI patients were retrospectively collected. Patients were divided into a Heart failure group and a non-heart failure group based on the occurrence of heart failure during hospitalization. Comparative analyses were performed between the two groups. Multivariate logistic regression analysis was used to identify risk factors of in-hospital heart failure. A nomogram prediction model was constructed using R software. The model's performance was evaluated by receiver operating characteristic (ROC) curve analysis, 10-fold cross-validation (repeated 100 times), and decision curve analysis.

Results: Among the 312 AMI patients, 94 (30.13%) developed heart failure during hospitalization. Multivariate logistic regression identified advanced age (OR = 2.158, P = 0.004), diabetes (OR = 1.964, P = 0.002), higher Gensini score (OR = 2.869, P = 0.001), left ventricular ejection fraction (LVEF) < 50% (OR = 2.581, P = 0.007), and elevated N-terminal pro B-type natriuretic peptide (NT-proBNP) levels (OR = 3.593, P < 0.001) as risk factors for heart failure in AMI patients. The constructed nomogram model demonstrated an area under the ROC curve (AUC) of 0.882, indicating good discriminative ability. The model demonstrated high stability through 100 repetitions of 10-fold cross-validation. Decision curve analysis confirmed its clinical utility.

Conclusion: In-hospital heart failure in AMI patients is associated with older age, diabetes, elevated Gensini score, reduced LVEF, and increased NT-proBNP levels. The developed nomogram model effectively predicts the risk of heart failure in this population and may assist in early clinical risk stratification.